Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3368 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.1987. Min Act: -0.0000

Data Index: 784978 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.1815. Min Act: -0.0000

Data Index: 265679 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.1854. Min Act: -0.0000

Data Index: 1860089 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1161288 (The Pile)

Max Activating Token Index: 264

Text #4

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0849. Min Act: -0.0000

Data Index: 109693 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 1.1987. Min Range: -1.1987

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1756050 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9694. Min Act: -0.0000

Data Index: 794885 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1463784 (The Pile)

Max Activating Token Index: 704

Text #8

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1847907 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9016. Min Act: -0.0000

Data Index: 881039 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9183. Min Act: -0.0000

Data Index: 580556 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9341. Min Act: -0.0000

Data Index: 758965 (The Pile)

Max Activating Token Index: 259

Text #12

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1733845 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8965. Min Act: -0.0000

Data Index: 238455 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8780. Min Act: -0.0000

Data Index: 98412 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8593. Min Act: -0.0000

Data Index: 783090 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8464. Min Act: 0.0000

Data Index: 1996737 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1723207 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1146951 (The Pile)

Max Activating Token Index: 900

Text #19

Max Range: 1.1987. Min Range: -1.1987

Max Act: 0.8464. Min Act: -0.0000

Data Index: 490867 (The Pile)

Max Activating Token Index: 636